P
Patrick MacAlpine
Researcher at University of Texas at Austin
Publications - 34
Citations - 785
Patrick MacAlpine is an academic researcher from University of Texas at Austin. The author has contributed to research in topics: Humanoid robot & Reinforcement learning. The author has an hindex of 15, co-authored 33 publications receiving 570 citations.
Papers
More filters
Journal ArticleDOI
Outracing champion Gran Turismo drivers with deep reinforcement learning
Peter R. Wurman,Sam C. Barrett,Kenta Kawamoto,James MacGlashan,Kaushik Subramanian,Tom Walsh,Roberto Capobianco,Alisa Devlic,Franziska Eckert,Florian Fuchs,Leilani H. Gilpin,Piyush Khandelwal,Varun J. Kompella,HaoChih Lin,Patrick MacAlpine,Declan Danesh Oller,Takuma Seno,Craig Sherstan,Mick Thomure,Houmehr Aghabozorgi,Leon Barrett,Rory Douglas,Dion J. Whitehead,Peter Dürr,Peter Stone,Michael Spranger,Hiroaki Kitano +26 more
TL;DR: In this article , the authors describe how they trained agents for Gran Turismo that can compete with the world's best e-sports drivers, and demonstrate the possibilities and challenges of using these techniques to control complex dynamical systems in domains where agents must respect imprecisely defined human norms.
Proceedings ArticleDOI
Humanoid robots learning to walk faster: from the real world to simulation and back
TL;DR: GSL is introduced, an iterative optimization framework for speeding up robot learning using an imperfect simulator, and is fully implemented and validated on the task of learning to walk using an Aldebaran Nao humanoid robot.
Proceedings Article
Design and optimization of an omnidirectional humanoid walk: a winning approach at the RoboCup 2011 3D simulation competition
TL;DR: The design and learning architecture for an omnidirectional walk used by a humanoid robot soccer agent acting in the RoboCup 3D simulation environment is presented, the first time that robot behavior has been conceived and constructed on a real robot for the end purpose of being used in simulation.
Proceedings ArticleDOI
On optimizing interdependent skills: a case study in simulated 3D humanoid robot soccer
TL;DR: A learning architecture for a humanoid robot soccer agent that has been fully deployed and tested within the RoboCup 3D simulation environment is presented and a framework for optimizing skills in conjunction with one another is described, a little-understood problem with substantial practical significance.
Journal ArticleDOI
Variety Wins: Soccer-Playing Robots and Infant Walking.
TL;DR: It is proposed that robotics provides a fruitful avenue for testing hypotheses about infant development; reciprocally, observations of infant behavior may inform research on artificial intelligence.